In this work, we explore whether the recently demonstrated zero-shot abilities of the T0 model extend to Named Entity Recognition for out-of-distribution languages and time periods. Using a historical newspaper corpus in 3 languages as test-bed, we use prompts to extract possible named entities. Our results show that a naive approach for prompt-based zero-shot multilingual Named Entity Recognition is error-prone, but highlights the potential of such an approach for historical languages lacking labeled datasets. Moreover, we also find that T0-like models can be probed to predict the publication date and language of a document, which could be very relevant for the study of historical texts.

Cognates and borrowings carry different aspects of etymological evolution. In this work, we study semantic change of such items using multilingual word embeddings, both static and contextualised. We underline caveats identified while building and evaluating these embeddings. We release both said embeddings and a newly-built historical words lexicon, containing typed relations between words of varied Romance languages.

Character-based neural machine translation models have become the reference models for cognate prediction, a historical linguistics task. So far, all linguistic interpretations about latent information captured by such models have been based on external analysis (accuracy, raw results, errors). In this paper, we investigate what probing can tell us about both models and previous interpretations, and learn that though our models store linguistic and diachronic information, they do not achieve it in previously assumed ways.

Diachronic lexical information is not only important in the field of historical linguistics, but is also increasingly used in NLP, most recently for machine translation of low resource languages. Therefore, there is a need for fine-grained, large-coverage and accurate etymological lexical resources. In this paper, we propose a set of guidelines to generate such resources, for each step of the life-cycle of an etymological lexicon: creation, update, evaluation, dissemination, and exploitation. To illustrate the guidelines, we introduce EtymDB 2.0, an etymological database automatically generated from the Wiktionary, which contains 1.8 million lexemes, linked by more than 700,000 fine-grained etymological relations, across 2,536 living and dead languages. We also introduce use cases for which EtymDB 2.0 could represent a key resource, such as phylogenetic tree generation, low resource machine translation or medieval languages study.

La prédiction de cognats est une tâche clef de la linguistique historique et présente de nombreuses similitudes avec les tâches de traduction automatique. Cependant, alors que cette seconde discipline a vu fleurir l’utilisation de méthodes neuronales, celles-ci restent largement absentes des outils utilisés en linguistique historique. Dans ce papier, nous étudions donc la performance des méthodes neuronales utilisées en traduction (les réseaux encodeur-décodeur) pour la tâche de prédiction de cognats. Nous nous intéressons notamment aux types de données utilisables pour cet apprentissage et comparons les résultats obtenus, sur différents types de données, entre des méthodes statistiques et des méthodes neuronales. Nous montrons que l’apprentissage de correspondances phonétiques n’est possible que sur des paires de cognats, et que les méthodes statistiques et neuronales semblent avoir des forces et faiblesses complémentaires quant à ce qu’elles apprennent des données.

Cognate prediction and proto-form reconstruction are key tasks in computational historical linguistics that rely on the study of sound change regularity. Solving these tasks appears to be very similar to machine translation, though methods from that field have barely been applied to historical linguistics. Therefore, in this paper, we investigate the learnability of sound correspondences between a proto-language and daughter languages for two machine-translation-inspired models, one statistical, the other neural. We first carry out our experiments on plausible artificial languages, without noise, in order to study the role of each parameter on the algorithms respective performance under almost perfect conditions. We then study real languages, namely Latin, Italian and Spanish, to see if those performances generalise well. We show that both model types manage to learn sound changes despite data scarcity, although the best performing model type depends on several parameters such as the size of the training data, the ambiguity, and the prediction direction.